Patent · US Active

Device and method for training a normalizing flow

US11961275B2 · kind B2 · utility

0Cited by
0References
10Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 16, 2021
Grant dateApr 16, 2024
Priority date
Expiry dateNov 3, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/473
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computer-implemented method for training a normalizing flow. The normalizing flow predicts a first density value based on a first input image. The first density value characterizes a likelihood of the first input image to occur. The first density value is predicted based on an intermediate output of a first convolutional layer of the normalizing flow. The intermediate output is determined based on a plurality of weights of the first convolutional layer. The method for training includes: determining a second input image; determining an output, wherein the output is determined by providing the second input image to the normalizing flow and providing an output of the normalizing flow as output; determining a second density value based on the output tensor and on the plurality of weights; determining a natural gradient of the plurality of weights with respect to the second density value; adapting the weights according to the natural gradient.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.